gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
qwen3.8-27b-fable-fusion-f711-gain-mlx
LM-STUDIO MLXqwen3_5 · 27B · MXFP4
Aug 20, 2026 · Apple M4 Max
Global Score
76 vs 88
Hardware Fit
51 vs 70
Quality Score
87 vs 96
Hardware
gemma-3-27b-it-qat qwen3.8-27b-fable-…
MachineMac miniMacBook Pro
CPUApple M4 ProApple M4 Max
Cores1416
RAM64 GB128 GB
GPUApple M4 ProApple M4 Max
OSmacOS 15.7.4macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma-3-27b-it-qat qwen3.8-27b-fable-…
Tokens/sec8.930.4
First chunk3976 ms27 ms
TTFT4.0 s4.4 s
Load timeN/AN/A
Memory usage15.7 GB19.9 GB
Memory %25%16%
HW Fit Score Breakdown
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
qwen3.8-27b-fable-fusio…
Speed
34/50
TTFT
6/20
Memory
30/30
Quality
gemma-3-27b-it-qat
Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3.8-27b-fable-fusio…
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest